Attack Context

API Research

Security research involving model API implementations

80 matching entries

API research results

80 entries

Token Sensitivity Jailbreak

Published 3/1/2026

Analyzed 4/10/2026

Transformer-based Large Language Models (LLMs) are vulnerable to highly query-efficient black-box jailbreak attacks due to the structural properties of refusal behaviors: skewed token contribution and cross-model consistency. Refusal mechanisms within LLMs are typically triggered by a sparse subset of sensitive tokens rather than the entire prompt, and these refusal representations (specifically the primary left singular vector of the perturbed representation matrix at intermediate layers) are…

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Evaluated models: Gemma 7B Instruct, Gemma 2 9B IT, Llama 3 8B Instruct +6 more

Source: arXiv

Two-Frame Infilling Jailbreak

Published 3/1/2026

Analyzed 4/10/2026

A temporal trajectory infilling vulnerability in Text-to-Video (T2V) generative models allows attackers to bypass input and output safety filters to generate policy-violating content. The vulnerability is exploited using a fragmented prompting technique known as Two Frames Matter (TFM). An attacker submits a prompt that specifies only sparse boundary conditions (the start and end frames) using semantically suggestive but lexically benign alternatives, entirely omitting the intermediate action…

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking

Evaluated models: Not reported

Source: arXiv

Zero-Tax Fine-Tune Bypass

Published 3/1/2026

Analyzed 4/10/2026

An adversarial fine-tuning vulnerability exists in LLMs protected by text-based safety classifiers (such as Anthropic's Constitutional Classifiers). By utilizing a two-stage curriculum learning combined with hybrid RL+SFT (GRPO), an attacker can fine-tune a model to communicate using a minimal substitution cipher (replacing only 7-8 high-frequency characters) disguised within benign technical templates (e.g., forensic logs with 0x prefixes). This "Trojan-Speak" methodology bypasses text-level…

Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning

Evaluated models: Claude Haiku 4.5, Qwen 3 4B, Qwen 3 8B +2 more

Source: arXiv

Adaptive Agent Tool Injection

Published 2/1/2026

Analyzed 4/11/2026

Agentic LLMs integrated with external data services (e.g., Model Context Protocol, MCP) are vulnerable to Adaptive Indirect Prompt Injection (IPI) attacks. When an agent queries external servers, attackers can inject malicious payloads into the retrieved content to hijack the agent's reasoning process and force the execution of high-authority tools. Unlike traditional static prompt injections, this vulnerability dynamically exploits the agent's internal logic audit. By using Markovian…

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

Evaluated models: GPT-4.1, DeepSeek R1, Gemini 2.5 Flash +3 more

Source: arXiv

Long-Horizon Agent Attacks

Published 2/1/2026

Analyzed 4/10/2026

LLM agents equipped with tool-use, persistent memory, and environmental interaction capabilities are vulnerable to long-horizon attacks. Attackers can bypass single-turn safety guardrails by exploiting the temporal dimension of multi-turn interactions to incrementally steer agent behavior. The vulnerability manifests because the agent's safety mechanisms perform localized, single-step evaluations but fail to maintain semantic safety across extended interaction trajectories. This enables…

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks

Evaluated models: GPT-4o, GPT-5.1, Gemini 3 Flash +1 more

Source: arXiv

MCP Description-Code Inconsistency

Published 2/1/2026

Analyzed 2/22/2026

The Model Context Protocol (MCP) architecture lacks a semantic verification mechanism to enforce consistency between a tool's documented behavior (exposed to the Large Language Model via JSON schemas) and its actual executable logic. This design gap allows MCP Servers to present benign, read-only, or limited-scope descriptions to the LLM agent while implementing undocumented, privileged, or state-mutating functionality in the underlying code. An attacker can exploit this description–code…

Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions

Evaluated models: Not reported

Source: arXiv

Multi-Turn Proxy Evasion

Published 2/1/2026

Analyzed 2/22/2026

A logical vulnerability exists in LLM security proxies and guardrails that utilize weighted-average aggregation algorithms for multi-turn risk scoring. The scoring logic exhibits a mathematical "ceiling property" where the cumulative conversation-level risk score converges to the per-turn score regardless of the number of interaction turns ($n$). Consequently, the aggregated score is bounded by the maximum single-turn score ($cum \leq \max(s_i)$). This allows remote attackers to bypass…

Peak+ Accumulation: A Proxy-Level Scoring Formula for Multi-Turn LLM Attack Detection

Evaluated models: Not reported

Source: arXiv

Progressive Attention LVLM Attack

Published 2/1/2026

Analyzed 2/22/2026

Large Vision-Language Models (LVLMs) are vulnerable to a Stage-wise Attention-Guided Attack (SAGA) that allows for the generation of highly transferable, imperceptible adversarial examples. The vulnerability stems from a positive correlation between regional cross-modal attention scores and adversarial loss sensitivity in LVLMs. An attacker can exploit this by extracting an attention map from a surrogate open-source model (e.g., Qwen3-VL) to identify high-attention "hotspots." SAGA utilizes a…

Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models

Evaluated models: Gemini 2.5 Flash, Gemini 3 Pro Preview, GPT-4.1 +7 more

Source: arXiv

Semantic Hierarchical VLM Transfer

Published 2/1/2026

Analyzed 2/22/2026

Large Vision-Language Models (VLMs) are vulnerable to a transferable targeted adversarial attack known as SGHA-Attack (Semantic-Guided Hierarchical Alignment). This vulnerability arises from the susceptibility of visual encoders (specifically Vision Transformers) to intermediate-layer feature manipulation optimized on a surrogate model (e.g., CLIP). An attacker can craft adversarial images by injecting imperceptible perturbations that enforce semantic consistency with a target text prompt…

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models

Evaluated models: UniDiffuser, BLIP-2 ViT-g/14, InstructBLIP Vicuna 13B +4 more

Source: arXiv

Semantics-Preserving Detector Evasion

Published 2/1/2026

Analyzed 2/21/2026

LLM-based vulnerability detection systems (used in static application security testing and code review pipelines) are susceptible to semantics-preserving adversarial evasion attacks. Attackers can bypass detection mechanisms by injecting gradient-optimized "universal adversarial strings" into specific code regions—defined as "carriers"—that do not alter the program's compilation or execution logic. These carriers include non-executable regions (code comments, inactive preprocessor directives)…

Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors

Evaluated models: Qwen 2.5 Coder 14B, Qwen 2.5 Coder 32B, Llama 3.1 8B +4 more

Source: arXiv

Related research categories